OCR challenge for index cards

The goal of this task is to post-process the output from the Tesseract OCR engine. Alternatively, it could be treated as an OCR, as images are also available. [ver. 1.0.2]

Log in to write a comment

s444415   2023-03-23 11:49

submitted a solution:Donut trained on wikisource

s444415   2023-03-21 08:35

submitted a solution:Donut fine tuned wikisource yellow

s444415   2023-01-05 15:02

submitted a solution:Donut fine tune with data from challange

s444415   2022-12-22 13:58

submitted a solution:Donut fine tuned

s444415   2022-12-22 13:51

submitted a solution:Donut base model

s444415   2022-12-22 13:46

submitted a solution:Donut proto model

p/tlen   2021-04-09 16:01

submitted a solution:Baseline - just rewrite Tesseract output